18894493. SYSTEMS AND METHODS FOR NEURAL-NETWORK BASED VIDEO ENCODING (ROVI GUIDES, INC.)
SYSTEMS AND METHODS FOR NEURAL-NETWORK BASED VIDEO ENCODING
Organization Name
Inventor(s)
Zhu Li of Overland Park KS (US)
SYSTEMS AND METHODS FOR NEURAL-NETWORK BASED VIDEO ENCODING
This abstract first appeared for US patent application 18894493 titled 'SYSTEMS AND METHODS FOR NEURAL-NETWORK BASED VIDEO ENCODING
Original Abstract Submitted
A system and method are provided for encoding frames of 3D media content. The system trains first and second neural networks based on the voxel geometry information of their respective frames, such that the neural network is configured to receive a coordinate of a voxel and output color attributes information for the voxel. The trained neural network comprises a plurality of weights for each layer of the neural network. The system generates encoding data for the first frame by storing each respective decomposition data of a first plurality of matrices generated based on the plurality of weights for each layer of the first neural network. The system generates encoding data for the second frame by storing differences between the decomposition data of the second plurality of matrices and the decomposition data of the first plurality of matrices.
